DOI QR코드

DOI QR Code

엔트로피 기반 ECoG 신호를 이용한 손과 팔꿈치 움직임 추론

Entropy-based Discrimination of Hand and Elbow Movements Using ECoG Signals

  • Kim, Ki-Hyun (School of Electronic Engineering, Soongsil University) ;
  • Cha, Kab-Mun (School of Electronic Engineering, Soongsil University) ;
  • Rhee, Kiwon (School of Electronic Engineering, Soongsil University) ;
  • Chung, Chun Kee (Department of Neurosurgery, Seoul National University College of Medicine) ;
  • Shin, Hyun-Chool (School of Electronic Engineering, Soongsil University)
  • 투고 : 2013.11.12
  • 심사 : 2013.11.19
  • 발행 : 2013.12.30

초록

본 논문에서는 Electrocorticogram(ECoG) 신호를 이용하여 손과 팔꿈치의 움직임을 추론하는 방법을 제안한다. 환자로부터 다수의 채널을 이용하여 표면 근전도 신호와 ECoG 신호를 동시에 취득하였다. 추론하는 동작은 손을 쥐었다 펴는 동작과 팔꿈치를 안으로 굽히는 동작이며, 외부 자극에 의해 동작을 수행하는 방법 대신 환자의 자유의지에 의해 동작을 수행하게 하였다. 표면 근전도 신호를 이용하여 동작을 수행한 운동 시점을 찾고, ECoG 신호를 이용하여 동작을 추론한다. 각 동작의 특징을 추출하기 위하여 ECoG 신호를 전체 대역을 포함한 ${\delta}$, ${\Theta}$, ${\alpha}$, ${\beta}$, ${\gamma}$ 총 6개의 대역을 나누어 정보 엔트로피를 구하고, 최대우도추정법을 사용하여 동작을 추정하였다. 실험 결과 감마대역의 ECoG를 사용할 경우 다른 대역을 사용할 때 보다 높은 평균 74%의 성능을 보이며, 다른 대역보다 감마 대역에서 높은 추정 성공률을 보였다. 또한 운동 시점을 기준으로 3개의 시간 구간으로 나누어 준비전위를 포함하는 'before' 구간과 'onset' 구간을 비교하였다. 'before' 구간과 'onset' 구간에서 추정 성공률은 각각 66%, 65%로 준비전위를 이용할 수 있다는 것을 알 수 있었다.

In this paper, a method of estimating hand and elbow movements using electrocorticogram (ECoG) signals is proposed. Using multiple channels, surface electromyogram (EMG) signals and ECoG signals were obtained from patients simultaneously. The estimated movements were those to close and then open the hand and those to bend the elbow inward. The patients were encouraged to perform the movements in accordance with their free will instead of after being induced by external stimuli. Surface EMG signals were used to find movement time points, and ECoG signals were used to estimate the movements. To extract the characteristics of the individual movements, the ECoG signals were divided into a total of six bands (the entire band and the ${\delta}$, ${\Theta}$, ${\alpha}$, ${\beta}$, and ${\gamma}$ bands) to obtain the information entropy, and the maximum likelihood estimation method was used to estimate the movements. The results of the experiment showed the performance averaged 74% when the ECoG of the gamma band was used, which was higher than that when other bands were used, and higher estimation success rates were shown in the gamma band than in other bands. The time of the movements was divided into three time sections based on movement time points, and the "before" section, which included the readiness potential, was compared with the "onset" section. In the "before" section and the "onset" section, estimation success rates were 66% and 65%, respectively, and thus it was determined that the readiness potential could be used.

키워드

참고문헌

  1. Nuri F. Ince, Fikri Goksu and Ahmed H. Tewfik, "An ECoG based brain computer interface with spatially adapted time frequency patterns," International Conference on Bio-inspired Systems and Signal Processing, Portugal, Jan, 2008
  2. Kai J. Miller, Pradeep Shenoy, Marcel den Nijs, Larry B. Sorensen, Rajesh P. N. Rao, and Jeffrey G. Ojemann, "Beyond the gamma band: the role of high-frequency features in movement classification", IEEE Transactions on Biomedical Engineering, vol. 55, no. 5, pp. 1634-1637, May, 2008 https://doi.org/10.1109/TBME.2008.918569
  3. Yuan Yuan, An-bang Xu, Ping Guo and Jia-cai Zhang, "ECoG Analysis with Affinity Propagation Algorithm", IEEE Natural Computation, Fourth International Conference, vol. 5, pp. 52-56, 2008
  4. Mingai Li, Jinfu Yang, Dongmei Hao and Songmin Jia , "ECoG Recognition of Motor Imagery Based on SVM Ensemble", IEEE International Conference on Robotics and Biomimetics, pp. 1967-1972, Dec, 2009
  5. Hai-bin Zhao, Chun-yang Yu, Chong Liu and Hong Wang, "ECoG-based Brain-Computer Interface Using Relative Wavelet Energy and Probabilistic Neural Network", 3rd International Conference on Biomedical Engineering and Informatics, vol. 2, pp. 873-877, 2010
  6. Nathan E. Crone, Diana L. Miglioretti, Barry Gordon and Ronald P. Lesser, "Functional mapping of human sensorimotor cortex with electrocorticographic spectral analysis. II. Event-related synchronization in the gamma band", oxford: Brain, vol. 121, pp. 2301-231, 1998 https://doi.org/10.1093/brain/121.12.2301
  7. V. Menon, W. J. Freeman, B. A. Cutillo , J. E. Desmond, M. F. Ward, S. L. Bressler, K. D. Laxer, N. Barbaro and A. S. Gevins, "Spatio-temporal correlations in human gamma band electrocorticograms", Electroencephalography and Clinical Neurophysiology, vol. 98, no. 2, pp. 89-102, 1996 https://doi.org/10.1016/0013-4694(95)00206-5
  8. Kyung-Jin You, Hyun-Chool Shin, "Classifying Finger Flexing Motions with Surface EMG Using Entropy and The Maximum Likelihood Method", Journal of the Institute of Electronics Engineers of Korea, vol. SC, no. 6, pp. 38-43, Nov. 2009
  9. Jean-François Bercher and Christophe Vignat "Estimating the Entropy of a Signal with Applications", IEEE Transactions on Signal Processing, vol. 48, no. 6, Jun, 2000